Privacy‑Preserving Active Learning for bio‑inspired soft robotics maintenance with embodied agent feedback loops

Описание и применение

Использование автономных сигналов неопределённости робота позволяет обучать модель обслуживания без передачи сырых данных, соблюдая конфиденциальность.

Задача

A soft‑gripper’s proprietary sensor data could not be sent to a cloud model, yet failure prediction required data collection.

Результат

The embodied agent’s own uncertainty signals enabled privacy‑preserving active learning, reducing the need for raw data transfer while improving failure prediction.

Рабочий процесс

• 1. Estimate uncertainty on‑device using an ensemble of quantized MLPs and proprioceptive prediction error.
• 2. Select a small, informative subset of experiences based on combined uncertainty.
• 3. Clip, add noise, and aggregate selected updates federated‑style with differential privacy guarantees.
• 4. Push updated model back to the fleet and adjust robot behavior accordingly.

Доказательства

The lab that owned the robot didn’t want raw sensor streams leaving the device.

Источник

The robot estimates where its maintenance model is uncertain, using both ensemble disagreement and proprioceptive prediction error.

Источник

Selected updates are clipped, noised, and aggregated federated‑style, with differential privacy guarantees.

Источник